© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12429
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bea" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "ub" or "ea" from names or titles

    np_acts-logits-general · gemini-2.0-flash

    Beaubien, Beavers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.61
    excluded
    -0.60
    jstor
    -0.58
    tanleria
    -0.57
    bellar
    -0.56
    Примітки
    -0.55
     nltk
    -0.54
    trecht
    -0.54
    Sucesor
    -0.54
    rrggbb
    -0.52
    POSITIVE LOGITS
    ings
    0.66
    INGS
    0.57
    sel
    0.56
    ming
    0.55
    chable
    0.53
    lessly
    0.52
    DoubleQuotes
    0.52
    gles
    0.52
    mless
    0.52
    mspace
    0.50
    Activations Density 0.156%

    No Known Activations